Coding work
Code generation, repair, and software-engineering tasks
Gemini 3.7 Flash
Gemini 3.7 Flash leads on the public coding lane, 60.3 to 24.6, with Supported evidence for both models and non-overlapping 90% intervals.
Confidence: stronger
Gemini 2.5 Pro vs Gemini 3.7 Flash
Updated September 27, 2026. Rank says Gemini 3.7 Flash is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.
Both of these models will change. Get the price, version and retirement notices for the pair, each with its source. Follow model changes
Share or export
Decision reading
Gemini 3.7 Flash has the higher public score estimate, 67.66 versus 50.24, but the 90% score intervals overlap. Treat that as a lead, not a settled winner. 1 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
- Shared results
- 1
- Gemini 2.5 Pro only
- 7
- Gemini 3.7 Flash only
- 24
- Like-for-like categories
- 2 / 8
Supported: Gemini 2.5 Pro and Gemini 3.7 FlashHow the comparison works
Which one for your work
Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.
Chat turn cost
1K fresh input + 500 output tokens
Gemini 3.7 Flash
Gemini 3.7 Flash has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-ratesCache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Gemini 3.7 Flash
Gemini 3.7 Flash has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Show secondary and unsupported calls
Repository review cost
50K fresh input + 3K output tokens
Gemini 3.7 Flash
Gemini 3.7 Flash has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-ratesAgentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
Gemini 2.5 Pro is scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.
Confidence: limitedLong documents
Prompts that approach the documented context limit
No clear pick
The documented context windows are equal.
Confidence: documented
Which one for a specific job
Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.
The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.
24.6Gemini 2.5 Pro60.3Gemini 3.7 Flash
Like-for-like · BenchAlign v5.7
Gemini 3.7 Flash leads the like-for-like coding row.
Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.
Same basis rules as the category table below
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
7 Gemini 2.5 Pro only
1 Shared
24 Gemini 3.7 Flash only
1 category rests on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
Shape of the matched evidence
Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.
A shared-evidence shape is not available.
BenchLM does not draw a radar or infer missing axes when the matched evidence is too sparse.
Category results, on a stated basis
Each row shows the public-lane category score for both models: the BenchAlign v5.7 lane for agentic, coding, and knowledge, and the weighted public rows elsewhere, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence or the same weighted set. Directional and not-comparable rows remain visible, but they never receive a winner.
Coding
Like-for-like- Gemini 2.5 Pro
- 24.6
- Supported · #102/135
- Gemini 3.7 Flash
- 60.3
- Supported · #17/135
- Basis
- BenchAlign v5.7 lane · 3 vs 6 public rows
- Reading
- Gemini 3.7 Flash leads
Knowledge
Like-for-like- Gemini 2.5 Pro
- 44.2
- Supported · #74/158
- Gemini 3.7 Flash
- 71.1
- Supported · #10/158
- Basis
- BenchAlign v5.7 lane · 2 vs 6 public rows
- Reading
- Gemini 3.7 Flash leads
Agentic
Directional only- Gemini 2.5 Pro
- 24.7
- Estimated · #80/105
- Gemini 3.7 Flash
- 58.6
- Supported · #20/105
- Basis
- BenchAlign v5.7 lane · 1 vs 7 public rows
- Reading
- Directional only
Reasoning
Not comparable- Gemini 2.5 Pro
- 69.5
- Unranked · 2 rankable rows
- Gemini 3.7 Flash
- 77.8
- Unranked · 5 rankable rows
- Basis
- Provisional lane · 0 vs 1 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- Gemini 2.5 Pro
- 70.4
- Unranked · 1 rankable row
- Gemini 3.7 Flash
- 82.6
- #10/50
- Basis
- Provisional lane · 0 vs 1 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- Gemini 2.5 Pro
- Not ranked
- Gemini 3.7 Flash
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- Gemini 2.5 Pro
- 56.4
- #76/124
- Gemini 3.7 Flash
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- Gemini 2.5 Pro
- 35.1
- Unranked · 2 rankable rows
- Gemini 3.7 Flash
- Not ranked
- Basis
- Provisional lane · 2 vs 0 weighted rows
- Reading
- Not comparable
| Category | Gemini 2.5 Pro | Gemini 3.7 Flash | Basis | Reading |
|---|---|---|---|---|
| Coding | 24.6Supported · #102/135 | 60.3Supported · #17/135 | Like-for-likeBenchAlign v5.7 lane · 3 vs 6 public rows | Gemini 3.7 Flash leads |
| Knowledge | 44.2Supported · #74/158 | 71.1Supported · #10/158 | Like-for-likeBenchAlign v5.7 lane · 2 vs 6 public rows | Gemini 3.7 Flash leads |
| Agentic | 24.7Estimated · #80/105 | 58.6Supported · #20/105 | Directional onlyBenchAlign v5.7 lane · 1 vs 7 public rows | Directional only |
| Reasoning | 69.5Unranked · 2 rankable rows | 77.8Unranked · 5 rankable rows | Not comparableProvisional lane · 0 vs 1 weighted rows | Not comparable |
| Multimodal | 70.4Unranked · 1 rankable row | 82.6#10/50 | Not comparableProvisional lane · 0 vs 1 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Instruction following | 56.4#76/124 | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | 35.1Unranked · 2 rankable rows | Not ranked | Not comparableProvisional lane · 2 vs 0 weighted rows | Not comparable |
Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign v5.7) differ from the provisional-lane categories. Unranked scores sit on the provisional lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.
Supported evidence per lane · bars run 0–100Methodology
What each workload costs
Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.
Chat turn
1K fresh input + 500 output tokens
- Gemini 2.5 Pro
- $0.00625
- Fits in one request
- Gemini 3.7 Flash
- $0.00262
- Fits in one request
Gemini 3.7 Flash has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- Gemini 2.5 Pro
- $0.0925
- Fits in one request
- Gemini 3.7 Flash
- $0.04875
- Fits in one request
Gemini 3.7 Flash has the lower modeled cost
Costs use the listed standard API rates.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Gemini 2.5 Pro
- $0.15
- Fits in one request
- Gemini 3.7 Flash
- $0.0675
- Fits in one request
Gemini 3.7 Flash has the lower modeled cost
Costs use the listed standard API rates.
Cached input falls back to the list input rate only where a cached rate is unpublished
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationGemini 2.5 ProGemini 3.7 Flash
Context window
Maximum documented context; output-token limits may be lower.
Gemini 2.5 Pro
Gemini 3.7 Flash
API model ID
Gemini 2.5 Pro
gemini-2.5-pro
Google Gemini API pricingGemini 3.7 Flash
gemini-3.7-flash
Google Gemini 3.7 Flash API documentationCached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Gemini 2.5 Pro
$0.125 per 1M cached input tokens
Google Gemini API pricingGemini 3.7 Flash
$0.075 per 1M cached input tokens
Google Gemini API pricingDocumented inputs
Gemini 2.5 Pro
Not sourced
Gemini 3.7 Flash
text, image, video, audio, pdf
Google Gemini 3.7 Flash API documentationDocumented outputs
Gemini 2.5 Pro
Not sourced
Gemini 3.7 Flash
Provider availability
Gemini 2.5 Pro
Not sourced
Gemini 3.7 Flash
Generally Available · Gemini API, Google AI Studio, Gemini App - Spark, Gemini Enterprise App, Gemini Enterprise Agent Platform, Google Antigravity
Google DeepMind Gemini 3.7 Flash model cardReasoning profile
Gemini 2.5 Pro
Non-Reasoning
Gemini 3.7 Flash
Reasoning
Weight access
Gemini 2.5 Pro
Proprietary
Gemini 3.7 Flash
Proprietary
License
Gemini 2.5 Pro
Proprietary
Gemini 3.7 Flash
Proprietary
Release date
Gemini 2.5 Pro
2025-03-01
Gemini 3.7 Flash
2026-08-13
If you already use one of these models
- Deployment change
- Both entries list Google as the provider. Confirm endpoint, model ID, limits, and feature support before switching.
- Quality signal
- Gemini 3.7 Flash has the higher public score estimate, 67.66 versus 50.24, but the 90% score intervals overlap.
- Workload cost
- Repository review: $0.0925 vs $0.04875. Cache-heavy agent loop: $0.15 vs $0.0675.
- Context tradeoff
- Both models list 1M.
Run the same representative tasks against both endpoints before changing production traffic.
Questions
Which is better, Gemini 2.5 Pro or Gemini 3.7 Flash?
Gemini 3.7 Flash has the higher public score estimate, 67.66 versus 50.24, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.
Which is better for coding, Gemini 2.5 Pro or Gemini 3.7 Flash?
Gemini 3.7 Flash leads the public coding lane, 60.3 to 24.6, with Supported evidence for both models and non-overlapping 90% intervals.
Which is better for agentic tasks, Gemini 2.5 Pro or Gemini 3.7 Flash?
Gemini 3.7 Flash scores higher for agentic tasks on the public lane, 58.6 to 24.7. Gemini 2.5 Pro is scored on Estimated evidence for agentic tasks, so the reading is directional rather than like-for-like. BenchLM does not name a winner for agentic tasks from a directional reading; read the shared benchmark rows directly and test the models on the same task set.
Which costs less, Gemini 2.5 Pro or Gemini 3.7 Flash?
For the stated presets, chat costs $0.00625 on Gemini 2.5 Pro and $0.00263 on Gemini 3.7 Flash; repository review costs $0.0925 and $0.04875; the cache-heavy agent loop costs $0.15 and $0.0675. Costs use the listed standard API rates.
Which has the larger context window, Gemini 2.5 Pro or Gemini 3.7 Flash?
Both models list the same context window, 1M.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence32 rows
Agentic
Gert Labs
Gemini 2.5 Pro42.01%SourceGemini 3.7 Flash—Not directly comparable
Terminal-Bench 2.1
Gemini 2.5 Pro—Gemini 3.7 Flash85.8%SourceNot directly comparable
Terminal-Bench 3.0
Gemini 2.5 Pro—Gemini 3.7 Flash14.9%SourceNot directly comparable
AutomationBench
Gemini 2.5 Pro—Gemini 3.7 Flash30.4%SourceNot directly comparable
OSWorld 2.0
Gemini 2.5 Pro—Gemini 3.7 Flash47.9%SourceNot directly comparable
Agents' Last Exam
Gemini 2.5 Pro—Gemini 3.7 Flash26.3%SourceNot directly comparable
Terminal-Bench 2.1 (Vals)
Gemini 2.5 Pro—Gemini 3.7 Flash77.5%SourceNot directly comparable
ApprenticeBench
Gemini 2.5 Pro—Gemini 3.7 Flash16%SourceNot directly comparable
Coding
SWE-bench Verified
Gemini 2.5 Pro63.8%SourceGemini 3.7 Flash—Not directly comparable
Vibe Code Bench
Gemini 2.5 Pro0.40%SourceGemini 3.7 Flash—Not directly comparable
SWE-bench (Vals)
Gemini 2.5 Pro54.4%SourceGemini 3.7 Flash80.8%SourceGemini 3.7 Flash leads this result
FrontierCode 1.1 Main
Gemini 2.5 Pro—Gemini 3.7 Flash43.6%SourceNot directly comparable
DeepSWE
Gemini 2.5 Pro—Gemini 3.7 Flash65.3%SourceNot directly comparable
Terminal-Bench 2.1
Gemini 2.5 Pro—Gemini 3.7 Flash85.8%SourceNot directly comparable
FrontierSWE v2
Gemini 2.5 Pro—Gemini 3.7 Flash20.3%SourceNot directly comparable
LiveCodeBench (Vals)
Gemini 2.5 Pro—Gemini 3.7 Flash88.7%SourceNot directly comparable
Reasoning
Multimodal
Knowledge
GPQA
Gemini 2.5 Pro83%SourceGemini 3.7 Flash—Not directly comparable
HLE
Gemini 2.5 Pro18.8%SourceGemini 3.7 Flash—Not directly comparable
HLE-Verified
Gemini 2.5 Pro—Gemini 3.7 Flash53.6%SourceNot directly comparable
LABBench2
Gemini 2.5 Pro—Gemini 3.7 Flash82.1%SourceNot directly comparable
BioMysteryBench (human-solvable)
Gemini 2.5 Pro—Gemini 3.7 Flash87.1%SourceNot directly comparable
BioMysteryBench (human-difficult)
Gemini 2.5 Pro—Gemini 3.7 Flash43.5%SourceNot directly comparable
GPQA Diamond (Vals)
Gemini 2.5 Pro—Gemini 3.7 Flash93.9%SourceNot directly comparable
MMLU-Pro (Vals)
Gemini 2.5 Pro—Gemini 3.7 Flash90.1%SourceNot directly comparable
Math
32 public results · 1 shared
Watch Gemini 2.5 Pro vs Gemini 3.7 Flash
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.
Last updated September 27, 2026